SIFER: Scale-Invariant Feature Detector with Error Resilience

Mainali, Pradip; Lafruit, Gauthier; Yang, Qiong; Geelen, Bert; Gool, Luc Van; Lauwereins, Rudy

doi:10.1007/s11263-013-0622-3

Cited by 69 publications

(38 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given the spatial Gaussian scale-space concept [24,34,44,46,47,59,60,67,70,106,111,120,123], a general methodology for spatial scale selection has been developed based on local extrema over spatial scales of scale-normalized differential entities [62,64,65,72,73]. This general method- 2 The spatial Laplacian applied to the first-and second-order temporal derivatives ∇ 2 (x,y) L t and ∇ 2 (x,y) L tt as well as the spatio-temporal Laplacian ∇ 2 (x,y,t) L computed from a video sequence in the UCF-101 dataset (Kayaking_g01_c01.avi) at 3 × 3 combinations of the spatial scales (bottom row) σ s,1 = 2 pixels, (middle row) σ s,2 = 4.6 pixels and (top row) σ s,3 = 10.6 pixels and the temporal scales (left column) σ τ,1 = 40 ms, (middle column) σ τ,2 = 160 ms and (right column) σ τ,3 = 640 ms with the spatial and temporal scale parameters in units of σ s = √ s and σ τ = √ τ and using a time-causal spatio-temporal scale-space representation with a logarithmic distribution of the temporal scale levels for c = 2 (image size: 320 × 172 pixels of original 320 × 240 pixels; frame 90 of 226 frames at 25 framesframes/s) ology has in turn been successfully applied to develop robust methods for image-based matching and recognition [5,41,52,68,74,84,86,87,89,90,[112][113][114] that are able to handle large variations of the size of the objects in the image domain and with numerous applications regarding object recognition, object categorization, multi-view geometry, construction of 3-D models from visual input,…”

Section: Figmentioning

confidence: 99%

Spatio-Temporal Scale Selection in Video Data

Lindeberg

2017

J Math Imaging Vis

View full text Add to dashboard Cite

This work presents a theory and methodology for simultaneous detection of local spatial and temporal scales in video data. The underlying idea is that if we process video data by spatio-temporal receptive fields at multiple spatial and temporal scales, we would like to generate hypotheses about the spatial extent and the temporal duration of the underlying spatio-temporal image structures that gave rise to the feature responses. For two types of spatio-temporal scale-space representations, (i) a non-causal Gaussian spatio-temporal scale space for offline analysis of pre-recorded video sequences and (ii) a time-causal and timerecursive spatio-temporal scale space for online analysis of real-time video streams, we express sufficient conditions for spatio-temporal feature detectors in terms of spatio-temporal receptive fields to deliver scale-covariant and scale-invariant feature responses. We present an in-depth theoretical analysis of the scale selection properties of eight types of spatio-temporal interest point detectors in terms of either: (i)-(ii) the spatial Laplacian applied to the first-and secondorder temporal derivatives, (iii)-(iv) the determinant of the spatial Hessian applied to the first-and second-order temporal derivatives, (v) the determinant of the spatio-temporal Hessian matrix, (vi) the spatio-temporal Laplacian and (vii)-(viii) the first-and second-order temporal derivatives of the determinant of the spatial Hessian matrix. It is shown that seven of these spatio-temporal feature detectors allow for provable scale covariance and scale invariance. Then, we describe a time-causal and time-recursive algorithm for detecting sparse spatio-temporal interest points from video streams and show that it leads to intuitively reasonable results. An experimental quantification of the accuracy of the spatio-temporal scale estimates and the amount of temporal delay obtained from these spatio-temporal interest point detectors is given, showing that: (i) the spatial and temporal scale selection properties predicted by the continuous theory are well preserved in the discrete implementation and (ii) the spatial Laplacian or the determinant of the spatial Hessian applied to the first-and second-order temporal derivatives leads to much shorter temporal delays in a timecausal implementation compared to the determinant of the spatio-temporal Hessian or the first-and second-order temporal derivatives of the determinant of the spatial Hessian matrix.

show abstract

Section: Figmentioning

confidence: 99%

Spatio-Temporal Scale Selection in Video Data

Lindeberg

2017

J Math Imaging Vis

View full text Add to dashboard Cite

show abstract

“…Those detectors are widely used with smartphones or microcomputers with low CPU power. KAZE features use non-linear scale-space [25], and the scale-invariant feature detector with error resilience (SIFER) uses a cosine-modulated Gaussian filter to construct scale-space [26], [27]. In addition, methods that employ direct polynomial approximation of filter kernels or multi-template images have also been proposed [28]- [30].…”

Section: Related Workmentioning

confidence: 99%

XY-Separable Scale-Space Filtering by Polynomial Representations and Its Applications

Koutaki¹,

Uchimura²

2017

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYIn this paper, we propose the application of principal component analysis (PCA) to scale-spaces. PCA is a standard method used in computer vision. Because the translation of an input image into scalespace is a continuous operation, it requires the extension of conventional finite matrix-based PCA to an infinite number of dimensions. Here, we use spectral theory to resolve this infinite eigenvalue problem through the use of integration, and we propose an approximate solution based on polynomial equations. In order to clarify its eigensolutions, we apply spectral decomposition to Gaussian scale-space and scale-normalized Laplacian of Gaussian (sLoG) space. As an application of this proposed method, we introduce a method for generating Gaussian blur images and sLoG images, demonstrating that the accuracy of such an image can be made very high by using an arbitrary scale calculated through simple linear combination. Furthermore, to make the scale-space filtering efficient, we approximate the basis filter set using Gaussian lobes approximation and we can obtain XY-Separable filters. As a more practical example, we propose a new Scale Invariant Feature Transform (SIFT) detector.

show abstract

“…The keypoint feature approaches enable us to uniformly handle visual objects with appearance variation by using geometric invariance. Many methods have been proposed after SIFT [2,3] year on year such as SURF [5], PCA-SIFT [6], FAST [7], AGAST [8], CARD [9], FREAK [10], SPADE [11], ORB [12], SIFER [13], DSIFER [14], which are pursuing a higher trade-off between computational complexity, robustness, and stability. We focus on keypoint feature with scale and rotation invariance.…”

Section: Introductionmentioning

confidence: 99%

“…SURF enabled online image processing by using, instead of LoG kernel, boxstacked kernel and integral image [16] with a certain sacrifice of rotation invariance. The other existing methods [6][7][8][9][10][11][12][13][14] also discussed more efficient approaches of scale space for robust keypoint feature. Thus, the performance depends heavily on how to generate and deal with scale space.…”

Section: Introductionmentioning

confidence: 99%

Efficient keypoint detection and description via polynomial regression of scale space

Okutani

Sugimoto

Kamata

2016

2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Keypoint detection and description using approximate continuous scale space are more efficient techniques than typical discretized scale space for achieving more robust feature matching. However, this state-of-the-art method requires high computational complexity to approximately reconstruct, or decompress, the value at an arbitrary point in scale space. Specifically, it has O(M 2 ) computational complexity where M is an approximation order. This paper presents an efficient scale space approach that provides decompression operation with O(M ) complexity without a loss of accuracy. As a result of the fact that the proposed method has much fewer variables to be solved, the least-square solution can be obtained through normal equation. This is easier to solve than the existing method which employs Karhunen-Loeve expansion and generalized eigenvalue problem. Experiments revealed that the proposed method performs as expected from the theoretical analysis.

show abstract

SIFER: Scale-Invariant Feature Detector with Error Resilience

Cited by 69 publications

References 31 publications

Spatio-Temporal Scale Selection in Video Data

Spatio-Temporal Scale Selection in Video Data

XY-Separable Scale-Space Filtering by Polynomial Representations and Its Applications

Efficient keypoint detection and description via polynomial regression of scale space

Contact Info

Product

Resources

About